Files
GenAIExamples/ChatQnA/kubernetes/chatQnA_gaudi.yaml
Steve Zhang afcb3a3523 Add e2e test of chatqna for genai example (#334)
* add e2e test of chatqna for genai example.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com>
Co-authored-by: mkbhanda <malini.bhandaru@intel.com>
Co-authored-by: daisy-ycguo <yingchun.guo@intel.com>
2024-06-27 19:05:59 +08:00

64 lines
1.6 KiB
YAML

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: gmc.opea.io/v1alpha3
kind: GMConnector
metadata:
labels:
app.kubernetes.io/name: gmconnector
app.kubernetes.io/managed-by: kustomize
gmc/platform: gaudi
name: chatqa
namespace: chatqa
spec:
routerConfig:
name: router
serviceName: router-service
nodes:
root:
routerType: Sequence
steps:
- name: Embedding
internalService:
serviceName: embedding-svc
config:
endpoint: /v1/embeddings
- name: TeiEmbeddingGaudi
internalService:
serviceName: tei-embedding-gaudi-svc
isDownstreamService: true
- name: Retriever
data: $response
internalService:
serviceName: retriever-svc
config:
endpoint: /v1/retrieval
- name: VectorDB
internalService:
serviceName: redis-vector-db
isDownstreamService: true
- name: Reranking
data: $response
internalService:
serviceName: reranking-svc
config:
endpoint: /v1/reranking
- name: TeiReranking
internalService:
serviceName: tei-reranking-svc
config:
endpoint: /rerank
isDownstreamService: true
- name: Llm
data: $response
internalService:
serviceName: llm-svc
config:
endpoint: /v1/chat/completions
- name: TgiGaudi
internalService:
serviceName: tgi-gaudi-svc
config:
endpoint: /generate
isDownstreamService: true